Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    segments of text that contain a high frequency of whitespace characters or punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -1.08
     متعلقه
    -1.07
    RegressionTest
    -1.06
     Signalez
    -1.06
     <=",
    -1.01
    uxxxx
    -1.00
     ModelExpression
    -1.00
     >=",
    -0.99
    -0.99
    MigrationBuilder
    -0.98
    POSITIVE LOGITS
    :
    0.53
     i
    0.50
     del
    0.48
     .
    0.47
    li
    0.46
    vi
    0.46
     (
    0.45
     E
    0.45
     vi
    0.45
    na
    0.45
    Act Density 0.890%

    No Known Activations